DINO-QPM adapts frozen DINOv2 models via average-pooled patch embeddings and a sparsity loss to deliver both higher classification accuracy and human-interpretable global explanations.
Pruning by block benefit: Exploring the properties of vision transformer blocks during domain adaptation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification
DINO-QPM adapts frozen DINOv2 models via average-pooled patch embeddings and a sparsity loss to deliver both higher classification accuracy and human-interpretable global explanations.